whisper-tiny-rf / README.md
Alnine9's picture
End of training
d2df8e5 verified
|
raw
history blame
1.7 kB
metadata
language:
  - fr
license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: Whisper Small french - RF
    results: []

Whisper Small french - RF

This model is a fine-tuned version of openai/whisper-tiny on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7760
  • Wer: 49.2308

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-05
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 10
  • training_steps: 50
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
3.4424 5.0 10 3.5394 57.6923
1.7535 10.0 20 1.9843 54.6154
0.7841 15.0 30 1.2915 45.3846
0.2479 20.0 40 0.9029 48.4615
0.1579 25.0 50 0.7760 49.2308

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2